̽��ֱ�� of Cambridge - Krittika D’Silva

Women in STEM: Krittika D'Silva

sc604 — Thu, 05 Mar 2020 07:49:51 +0000

My PhD research focuses on using machine learning algorithms and network metrics to model urban cities worldwide. A project I led examined the role of network and transport metrics to predict whether a business will survive or fail.

My work at the NASA Frontier Development Lab focused on space medicine. As we send astronauts on longer missions into deep space, they are exposed for longer periods of time to radiation and microgravity both of which create numerous physiological changes.

We're only just starting to understand these changes, but harnessing AI and wearable devices to monitor astronaut health in space and build autonomous systems of healthcare in space is imperative. I think it's really exciting work and isn't talked about nearly as much as it should be since it's important for all of our future missions to the moon, Mars, and beyond!

̽��ֱ��Pulse Lab is an innovation lab formed within the UN to harness data science insights for policy. I worked on modeling internal migration in Vanuatu to support future national resource allocation. ̽��ֱ��experience with the Global Pulse lab taught me about the importance of translating research insights into practice. It provided me with exposure to public policy which was work I found interesting and impactful.

On a daily basis my research primarily involves me reading papers or coding at my computer from the Department of Computer Science and Technology, in West Cambridge.

̽��ֱ��most interesting day I’ve had so far in academia was when I was invited to travel to the UN office in New Delhi, India to help lead and present at a workshop on the potential for machine learning in the public sector. It was an opportunity to meet with those outside my field and share current machine learning research that I found exciting!

Last year, I was invited to a private estate in Kent, for a day of tennis with HRH Prince Edward, the son of Queen Elizabeth II. I played in a doubles match against HRH and although I lost, it was a unique opportunity and one I’ll never forget!

I hope my work can utilise machine learning to have a positive impact on the world. ̽��ֱ��private sector has harnessed machine learning to support products, advertisements, and services. However, the public sector has been slower to use the potential of machine learning to support government decision making and inform policy. In the future, I expect technology to play a larger role in development efforts worldwide. After my studies, I hope to support this work using my background in technology.

Cambridge has been a fantastic place to do my PhD research. ̽��ֱ��professors, peers, and resources are world-class. I’ve been given funding to travel and present my work at top-tier conferences worldwide as well as to work on international collaborations. I have also had the flexibility and exposure to internship opportunities which have enabled me to work in new countries, fields, and projects.

My advice for women considering a career in a STEM field is to find role models in the field who can support and guide you over the course of your career. I’ve been fortunate to have had a number of mentors who have helped to find opportunities, think through career decisions, and network with others in the field. This mentorship has been priceless.

Krittika D'Silva is a PhD candidate in the Department of Computer Science and Technology, a Gates Cambridge Scholar and a member of Jesus College. Alongside her academic research in AI and machine learning, she has worked for NASA on monitoring astronaut health with AI and wearable devices, and for the UN in using data science to inform public policy. Here, she tells us about her motivation, goals, and how she ended up playing a tennis match against HRH Prince Edward.

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Location, location, location: researchers develop model to predict retail failure

sc604 — Mon, 08 Oct 2018 23:01:44 +0000

Using information from ten different cities around the world, the researchers, led by the ̽��ֱ�� of Cambridge, have developed a model that can predict with 80% accuracy whether a new business will fail within six months. ̽��ֱ��results will be presented at the ACM Conference on Pervasive and Ubiquitous Computing (Ubicomp), taking place this week in Singapore.

While the retail sector has always been risky, the past several years have seen a transformation of high streets as more and more retailers fail. ̽��ֱ��model built by the researchers could be useful for both entrepreneurs and urban planners when determining where to locate their business or which areas to invest in.

“One of the most important questions for any new business is the amount of demand it will receive. This directly relates to how likely that business is to succeed,” said lead author Krittika D’Silva, a Gates Scholar and PhD student at Cambridge's Department of Computer Science and Technology. “What sort of metrics can we use to make those predictions?”

D’Silva and her colleagues used more than 74 million check-ins from the location technology platform Foursquare from Chicago, Helsinki, Jakarta, London, Los Angeles, New York, Paris, San Francisco, Singapore and Tokyo; and data from 181 million taxi trips from New York and Singapore.

Using this data, the researchers classified venues according to the properties of the neighbourhoods in which they were located, the visit patterns at different times of day, and whether a neighbourhood attracted visitors from other neighbourhoods.

“We wanted to better understand the predictive power that metrics about a place at a certain point in time have,” said D’Silva.

Whether a business succeeds or fails is normally based on a number of controllable and uncontrollable factors. Controllable factors might include the quality or price of the store’s product, its opening hours and its customer satisfaction. Uncontrollable factors might include unemployment rates of a city, overall economic conditions and urban policies.

“We found that even without information about any of these uncontrollable factors, we could still use venue-specific, location-related and mobility-based features in predicting the likely demise of a business,” said D’Silva.

̽��ֱ��data showed that across all ten cities, venues that are popular around the clock, rather than just at certain points of day, are more likely to succeed. Additionally, venues that are in demand outside of the typical popular hours of other venues in the neighbourhood tend to survive longer. ̽��ֱ��data also suggested that venues in diverse neighbourhoods, with multiple types of businesses, tend to survive longer.

While the ten cities had certain similarities, the researchers also had to account for their differences.

“ ̽��ֱ��metrics that were useful predictors vary from city to city, which suggests that factors affect cities in different ways,” said D’Silva. “As one example, that the speed of travel to a venue is a significant metric only in New York and Tokyo. This could relate to the speed of transit in those cities or perhaps to the rates of traffic.”

To test the predictive power of their model, the researchers first had to determine whether a particular venue had closed within the time window of their data set. They then ‘trained’ the model on a subset of venues, telling the model what the features of those venues were in the first time window and whether the venue was open or closed in a second time window. They then tested the trained model on another subset of the data to see how accurate it was.

According to the researchers, their model shows that when deciding when and where to open a business, it is important to look beyond the static features of a given neighbourhood and to consider the ways that people move to and through that neighbourhood at different times of day. They now want to consider how these features vary across different neighbourhoods in order to improve the accuracy of their model.

Reference:
Krittika D’Silva et al. ‘ ̽��ֱ��Role of Urban Mobility in Retail Business Survival.’ Paper presented to the Ubicomp 2018, Singapore, 8-12 October 2018. https://ubicomp.org/ubicomp2018/program/program.html

Researchers have used a combination of location and transport data to predict the likelihood that a given retail business will succeed or fail.

One of the most important questions for any new business is the amount of demand it will receive.

Krittika D’Silva

toastbrot81

Regent Street

Yes

Licence type:

Attribution-Noncommerical